From fe6a471f17f8996d6bf9e665fe9ee335b5598924 Mon Sep 17 00:00:00 2001 From: willemjan Date: Sun, 26 Jul 2026 21:10:46 +0200 Subject: [PATCH] add PDF export (FR10) pdf_export.py builds a PDF report (summary stats, AGP chart, hypo/hyper event summaries) via fpdf2 + matplotlib rather than plotly's kaleido, to avoid bundling a Chromium build into the image just for this. The Export page lets the user pick which sections to include and a date range, then download the result to send to the hospital team. This completes all ten functional requirements in docs/requirements-reporting.md. Co-Authored-By: Claude Sonnet 5 --- pages/8_Export.py | 52 +++++++++++++++ pdf_export.py | 134 +++++++++++++++++++++++++++++++++++++++ requirements.txt | 2 + tests/test_pdf_export.py | 41 ++++++++++++ 4 files changed, 229 insertions(+) create mode 100644 pages/8_Export.py create mode 100644 pdf_export.py create mode 100644 tests/test_pdf_export.py diff --git a/pages/8_Export.py b/pages/8_Export.py new file mode 100644 index 0000000..14a1faf --- /dev/null +++ b/pages/8_Export.py @@ -0,0 +1,52 @@ +import requests +import streamlit as st + +from auth import require_auth +from nightscout_client import NightscoutConfigError +from pdf_export import AVAILABLE_SECTIONS, SECTION_EVENTS, build_report_pdf +from reporting import HIGH, LOW, VERY_HIGH, VERY_LOW, detect_events, summarize_events +from ui_common import load_range_data, select_period_days + +st.set_page_config(page_title="Glucose dashboard — Export", page_icon="📊", layout="wide") +require_auth() + +st.title("Export") +st.caption("Stel een PDF-rapport samen om naar het diabetesteam te sturen (FR10).") + +start, end, days = select_period_days(default_label="90 dagen") +sections = st.multiselect("Onderdelen", AVAILABLE_SECTIONS, default=AVAILABLE_SECTIONS) + +try: + glucose, _treatments = load_range_data(start, end) +except NightscoutConfigError as exc: + st.error(str(exc)) + st.stop() +except (requests.RequestException, ValueError) as exc: + st.error(f"Kon geen data ophalen van Nightscout: {exc}") + st.stop() + +if glucose.empty: + st.info("Geen glucosemetingen gevonden in deze periode.") + st.stop() + +events_summary = {} +if SECTION_EVENTS in sections: + levels = { + f"Hypo Level 1 (<{LOW})": (LOW, "below"), + f"Hypo Level 2 (<{VERY_LOW})": (VERY_LOW, "below"), + f"Hyper Level 1 (>{HIGH})": (HIGH, "above"), + f"Hyper Level 2 (>{VERY_HIGH})": (VERY_HIGH, "above"), + } + for label, (threshold, direction) in levels.items(): + events = detect_events(glucose, threshold, direction) + events_summary[label] = summarize_events(events, days) + +pdf_bytes = build_report_pdf(sections, glucose, events_summary, start, end) + +st.download_button( + "Download PDF", + data=pdf_bytes, + file_name=f"glucoserapport_{start.strftime('%Y%m%d')}_{end.strftime('%Y%m%d')}.pdf", + mime="application/pdf", +) +st.caption(f"Periode: {start.strftime('%d-%m-%Y')} t/m {end.strftime('%d-%m-%Y')}") diff --git a/pdf_export.py b/pdf_export.py new file mode 100644 index 0000000..20483d4 --- /dev/null +++ b/pdf_export.py @@ -0,0 +1,134 @@ +""" +PDF-rapportgeneratie voor geselecteerde rapportageonderdelen (FR10). + +Gebruikt fpdf2 (puur Python, geen systeemdependencies) voor de PDF-opbouw en +matplotlib voor een eenvoudige statische AGP-grafiek specifiek voor de PDF — +bewust niet dezelfde Plotly-figuren als op de pagina's zelf (die zouden +kaleido vereisen, met een ingebakken Chromium-build: een groter image en meer +Trivy-oppervlak, voor dit doel niet nodig). +""" + +from __future__ import annotations + +import io + +import matplotlib + +matplotlib.use("Agg") +import matplotlib.pyplot as plt +import pandas as pd +from fpdf import FPDF +from fpdf.enums import XPos, YPos + +from reporting import ( + agp_percentile_bands, + gmi_percent, + percent_cv, + sensor_active_percent, + tir_breakdown_5band, +) + +SECTION_SUMMARY = "Samenvatting" +SECTION_AGP = "AGP profiel" +SECTION_EVENTS = "Hypo-/hyperevents" + +AVAILABLE_SECTIONS = [SECTION_SUMMARY, SECTION_AGP, SECTION_EVENTS] + +_LINE_KWARGS = {"new_x": XPos.LMARGIN, "new_y": YPos.NEXT} + + +def _agp_figure_png(glucose: pd.DataFrame) -> bytes: + bands = agp_percentile_bands(glucose) + fig, ax = plt.subplots(figsize=(7, 3)) + hours = bands["minute_of_day"] / 60 + ax.fill_between(hours, bands["p5"], bands["p95"], alpha=0.15, color="#2a78d6", label="5e-95e pct") + ax.fill_between(hours, bands["p25"], bands["p75"], alpha=0.3, color="#2a78d6", label="25e-75e pct") + ax.plot(hours, bands["p50"], color="#2a78d6", linewidth=2, label="Mediaan") + ax.set_xlabel("Uur van de dag") + ax.set_ylabel("mmol/L") + ax.set_xlim(0, 24) + ax.legend(loc="upper right", fontsize=8) + fig.tight_layout() + + buf = io.BytesIO() + fig.savefig(buf, format="png", dpi=150) + plt.close(fig) + buf.seek(0) + return buf.getvalue() + + +def _add_summary_section(pdf: FPDF, glucose: pd.DataFrame, start, end) -> None: + mean_mmol = glucose["mmol"].mean() + tir = tir_breakdown_5band(glucose) + active_pct = sensor_active_percent(glucose, start, end) + + pdf.set_font("Helvetica", "B", 13) + pdf.cell(0, 8, "Samenvatting", **_LINE_KWARGS) + pdf.set_font("Helvetica", "", 11) + pdf.cell(0, 6, f"Sensordekking: {active_pct:.0f}%", **_LINE_KWARGS) + pdf.cell(0, 6, f"Gemiddelde glucose: {mean_mmol:.1f} mmol/L", **_LINE_KWARGS) + pdf.cell(0, 6, f"Geschat HbA1c (GMI): {gmi_percent(mean_mmol):.1f}%", **_LINE_KWARGS) + pdf.cell(0, 6, f"Variabiliteit (%CV): {percent_cv(glucose):.0f}%", **_LINE_KWARGS) + pdf.ln(2) + pdf.cell(0, 6, f"Zeer laag (<3.0 mmol/L): {tir['very_low']:.0f}%", **_LINE_KWARGS) + pdf.cell(0, 6, f"Laag (3.0-3.9 mmol/L): {tir['low']:.0f}%", **_LINE_KWARGS) + pdf.cell(0, 6, f"In bereik (3.9-10.0 mmol/L): {tir['in_range']:.0f}%", **_LINE_KWARGS) + pdf.cell(0, 6, f"Hoog (10.0-13.9 mmol/L): {tir['high']:.0f}%", **_LINE_KWARGS) + pdf.cell(0, 6, f"Zeer hoog (>13.9 mmol/L): {tir['very_high']:.0f}%", **_LINE_KWARGS) + pdf.ln(4) + + +def _add_agp_section(pdf: FPDF, glucose: pd.DataFrame) -> None: + pdf.set_font("Helvetica", "B", 13) + pdf.cell(0, 8, "AGP profiel", **_LINE_KWARGS) + png_bytes = _agp_figure_png(glucose) + pdf.image(io.BytesIO(png_bytes), w=180) + pdf.ln(4) + + +def _add_events_section(pdf: FPDF, events_summary: dict[str, dict]) -> None: + pdf.set_font("Helvetica", "B", 13) + pdf.cell(0, 8, "Hypo-/hyperevents", **_LINE_KWARGS) + pdf.set_font("Helvetica", "", 11) + for label, summary in events_summary.items(): + pdf.cell( + 0, + 6, + f"{label}: {summary['count']} events, gemiddeld {summary['avg_duration_minutes']:.0f} min, " + f"{summary['events_per_week']:.1f}/week", + **_LINE_KWARGS, + ) + pdf.ln(4) + + +def build_report_pdf( + sections: list[str], + glucose: pd.DataFrame, + events_summary: dict[str, dict], + start, + end, +) -> bytes: + """Bouw een PDF met de geselecteerde onderdelen. + + `events_summary` bevat vooraf berekende hypo/hyper-samenvattingen (label -> + resultaat van reporting.summarize_events), zodat deze module geen + event-detectie hoeft te herhalen. + """ + pdf = FPDF() + pdf.add_page() + pdf.set_font("Helvetica", "B", 16) + pdf.cell(0, 10, "Glucoserapport", **_LINE_KWARGS) + pdf.set_font("Helvetica", "", 11) + pdf.cell(0, 8, f"Periode: {start.strftime('%d-%m-%Y')} t/m {end.strftime('%d-%m-%Y')}", **_LINE_KWARGS) + pdf.ln(4) + + if not glucose.empty: + if SECTION_SUMMARY in sections: + _add_summary_section(pdf, glucose, start, end) + if SECTION_AGP in sections: + _add_agp_section(pdf, glucose) + + if SECTION_EVENTS in sections and events_summary: + _add_events_section(pdf, events_summary) + + return bytes(pdf.output()) diff --git a/requirements.txt b/requirements.txt index 8338c4d..21ad258 100644 --- a/requirements.txt +++ b/requirements.txt @@ -3,5 +3,7 @@ pandas>=2.2,<3.0 requests>=2.32,<3.0 plotly>=5.24,<6.0 python-dotenv>=1.0,<2.0 +matplotlib>=3.9,<4.0 +fpdf2>=2.7,<3.0 pytest>=8.0,<9.0 ruff>=0.6,<1.0 diff --git a/tests/test_pdf_export.py b/tests/test_pdf_export.py new file mode 100644 index 0000000..3d3b73d --- /dev/null +++ b/tests/test_pdf_export.py @@ -0,0 +1,41 @@ +from datetime import date + +import pandas as pd + +from pdf_export import SECTION_AGP, SECTION_EVENTS, SECTION_SUMMARY, build_report_pdf + + +def _sample_glucose(): + timestamps = pd.date_range("2026-01-01", periods=48, freq="30min") + return pd.DataFrame({"timestamp": timestamps, "mmol": [6.0 + (i % 5) for i in range(48)]}) + + +def test_build_report_pdf_produces_valid_pdf_bytes(): + glucose = _sample_glucose() + events_summary = { + "Hypo Level 1": {"count": 2, "avg_duration_minutes": 20.0, "events_per_week": 1.0}, + } + pdf_bytes = build_report_pdf( + [SECTION_SUMMARY, SECTION_AGP, SECTION_EVENTS], + glucose, + events_summary, + date(2026, 1, 1), + date(2026, 1, 2), + ) + assert isinstance(pdf_bytes, bytes) + assert pdf_bytes.startswith(b"%PDF") + assert len(pdf_bytes) > 500 + + +def test_build_report_pdf_handles_empty_glucose(): + empty = pd.DataFrame(columns=["timestamp", "mmol"]) + pdf_bytes = build_report_pdf( + [SECTION_SUMMARY, SECTION_AGP], empty, {}, date(2026, 1, 1), date(2026, 1, 2) + ) + assert pdf_bytes.startswith(b"%PDF") + + +def test_build_report_pdf_handles_no_sections_selected(): + glucose = _sample_glucose() + pdf_bytes = build_report_pdf([], glucose, {}, date(2026, 1, 1), date(2026, 1, 2)) + assert pdf_bytes.startswith(b"%PDF")